CN111462480B - Traffic image evidence verification method and device, computer equipment and storage medium - Google Patents
Traffic image evidence verification method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111462480B CN111462480B CN202010129265.7A CN202010129265A CN111462480B CN 111462480 B CN111462480 B CN 111462480B CN 202010129265 A CN202010129265 A CN 202010129265A CN 111462480 B CN111462480 B CN 111462480B
- Authority
- CN
- China
- Prior art keywords
- evidence
- information
- image
- vehicle
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a traffic image evidence verification method, a traffic image evidence verification device, a computer device and a storage medium. Based on an image processing technique, the method comprises: acquiring evidence to be detected uploaded by a terminal, wherein the evidence to be detected comprises image evidence and evidence obtaining scene information; identifying the image evidence to obtain evidence-obtaining vehicle information in the image evidence; detecting the evidence to be detected based on the evidence obtaining scene information and the evidence obtaining vehicle information according to a preset evidence detection strategy; and when the evidence to be detected passes the detection, taking the evidence to be detected as the evidence of traffic violation. By adopting the method, evidence auditing can be completed in time, evidence which does not meet the requirements can be detected in time, evidence which does not meet the requirements can be obtained again, and the accuracy of vehicle image evidence acquisition is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for verifying a traffic image evidence, a computer device, and a storage medium.
Background
Along with the year-by-year increase of the motor vehicle reserves, various motor vehicle illegal events are also soared, and great challenges are brought to the safety and smoothness of road traffic operation. In order to better maintain the road traffic safety and order of the motor vehicles, the traffic police department can collect evidence for vehicles violating the traffic rules, and the evidence is used as a final basis for violating the traffic rules.
When the evidence is collected and the vehicle image evidence is verified or identified, the specifications of the image, such as definition, pixel size and the like, can only be verified, and the fact content represented by the image evidence cannot be verified, so that the accuracy rate of collecting the vehicle image evidence is low.
Disclosure of Invention
Based on this, it is necessary to provide a traffic image evidence verification method, an apparatus, a computer device and a storage medium for improving the accuracy of collecting vehicle image evidence in view of the above technical problems.
A traffic image evidence verification method, the method comprising:
acquiring evidence to be detected uploaded by a terminal, wherein the evidence to be detected comprises image evidence and evidence obtaining scene information;
identifying the image evidence to obtain evidence-obtaining vehicle information in the image evidence;
detecting the evidence to be detected based on the evidence obtaining scene information and the evidence obtaining vehicle information according to a preset evidence detection strategy;
and when the evidence to be detected passes the detection, taking the evidence to be detected as the evidence of traffic violation.
In one embodiment, the step of detecting the evidence to be detected based on the forensics scene information and the forensics vehicle information according to a preset evidence detection strategy includes:
determining corresponding necessary information from a preset database according to the forensics scene information; the information in the preset database is used for distinguishing the necessary information corresponding to different forensics scene information;
and detecting the evidence to be detected according to the necessary information and the evidence obtaining vehicle information.
In one embodiment, the step of detecting the evidence to be detected according to the necessary information and the information of the forensics vehicle includes:
searching information in the evidence obtaining vehicle information according to the necessary information, and acquiring detection information corresponding to the necessary information;
when each item of the necessary information has corresponding detection information, the evidence to be detected passes the detection;
and when one or more items of detection information corresponding to the necessary information are missing, marking one or more items of detection information corresponding to the missing essential information, and sending the marked items of detection information to a terminal for displaying.
In one embodiment, the step of identifying the image evidence and obtaining the vehicle information forensics in the image evidence includes:
carrying out image recognition on the image evidence through an image recognition model to obtain image information;
and performing semantic conversion according to the image information to obtain the evidence obtaining vehicle information.
In one embodiment, the step of performing image recognition on the image evidence through an image recognition model to obtain image information includes:
the image recognition model carries out image recognition on the image evidence according to the attribute of the image evidence to obtain image information;
when the attribute of the image evidence is a scene image, the image recognition model recognizes the vehicle attribute, the license plate and the environment to obtain license plate data, vehicle attribute data and environment data;
taking the vehicle attribute data, the license plate data and the environment data as image information;
when the attribute of the image evidence is a notice sheet image, the image recognition model recognizes the notice sheet image to obtain notice sheet information;
and taking the notification list information as picture information.
In one embodiment, after the step of using the evidence to be detected as the evidence of traffic violation when the detection result is passing, the method further includes:
acquiring law enforcement information according to the traffic law violation evidence;
and establishing an illegal case according to the law enforcement information and the traffic violation evidence.
In one embodiment, the method further comprises:
when a vehicle information query instruction is received, acquiring corresponding content according to query content in the vehicle query instruction, and sending the corresponding content to a terminal, wherein the query content comprises vehicle illegal information query and/or vehicle archive information query.
A traffic image evidence verification apparatus, the apparatus comprising:
the evidence obtaining module to be detected is used for obtaining evidence to be detected uploaded by the terminal, and the evidence to be detected comprises image evidence and evidence obtaining scene information;
the image evidence identification module is used for identifying the image evidence to obtain the evidence-obtaining vehicle information in the image evidence;
the detection module is used for detecting the evidence to be detected based on the evidence obtaining scene information and the evidence obtaining vehicle information according to a preset evidence detection strategy;
and the illegal evidence confirmation module is used for taking the to-be-detected evidence as the traffic illegal evidence when the to-be-detected evidence passes the detection.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method when the processor executes the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method.
According to the traffic image evidence verification method, the device, the computer equipment and the storage medium, image identification is carried out on the image evidence uploaded by the terminal in real time in the evidence to be detected, evidence obtaining vehicle information obtained from the image evidence is obtained, evidence verification is timely completed according to a preset evidence detection strategy and based on evidence obtaining scene information and evidence obtaining vehicle information, the evidence to be detected is detected, evidence verification is timely completed, evidence which is obtained in a timely manner and does not meet requirements is detected, evidence which is obtained in a timely manner is obtained again aiming at the evidence which does not meet requirements, and the accuracy rate of collecting the vehicle image evidence is improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a method for verifying evidence of traffic images;
FIG. 2 is a flow diagram illustrating a method for evidence verification of traffic images in one embodiment;
FIG. 3 is an exemplary illustration of head image evidence for a vehicle being forensically viewed in one embodiment;
FIG. 4 is an exemplary illustration of a vehicle tail image evidence of a vehicle being forensically shown in one embodiment;
FIG. 5 is an interface diagram for loading image evidence of evidence to be detected in one embodiment;
FIG. 6 is an interface diagram of image evidence identifying evidence to be detected in one embodiment;
FIG. 7 is a block diagram showing the structure of a traffic image evidence verification apparatus according to an embodiment;
fig. 8 is a block diagram showing the construction of a traffic image evidence verification apparatus according to another embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The traffic image evidence verification method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 acquires the evidence to be detected uploaded by the terminal 102, wherein the evidence to be detected comprises image evidence and forensics scene information; the server 104 identifies the image evidence to obtain the vehicle information for evidence collection in the image evidence; detecting evidence to be detected based on forensics scene information and forensics vehicle information according to a preset evidence detection strategy; and when the evidence to be detected passes the detection, taking the evidence to be detected as the traffic violation evidence. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, law enforcement evidence collection devices, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a method for verifying traffic image evidence is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
step S220, obtaining evidence to be detected uploaded by the terminal, wherein the evidence to be detected comprises image evidence and evidence obtaining scene information.
The evidence to be detected includes image evidence and evidence obtaining scene information, a scene photo or video of a traffic police officer performing law enforcement on the scene of the image evidence is taken on the scene, the image evidence includes images of various angles of a vehicle to be proved, a notice sheet and the like, as shown in an example diagram of image evidence of a head of the vehicle to be proved shown in fig. 3, and as shown in an example diagram of image evidence of a tail of the vehicle to be proved shown in fig. 4, the image evidence can be one or more. The image evidence can be stored in the terminal in advance, and can also be shot by triggering a shooting function on the terminal when the traffic police personnel upload the image evidence through the terminal. The forensics scene information refers to which item of the traffic rule is violated by the forensics vehicle, such as: the method comprises the following steps of running red light, vehicle violation, running without a guide line and the like, wherein the evidence obtaining scene information is selected or filled by a traffic police through a terminal in an interface for uploading evidence to be detected, and the steps are as follows: the traffic police personnel find that a vehicle is illegal to stop, select an illegal stop button on an interface for uploading evidence to be detected, and can determine evidence obtaining scene information according to the selection illegal stop button.
In one scene, a traffic police officer finds that a vehicle is illegal to stop, enters an interface for uploading evidence to be detected by opening an evidence collection application program on a terminal, clicks a evidence obtaining control, enables the terminal to open a camera shooting function, shoots image evidence, and loads the shot image evidence to the interface for uploading the evidence to be detected, and loads the interface for loading the evidence to be detected as shown in fig. 5. And the traffic police colludes the corresponding evidence-taking scene, and after the traffic police clicks the next step, the terminal sends the server to the image evidence and the evidence-taking scene information.
And step S240, identifying the image evidence to obtain the vehicle information for evidence collection in the image evidence.
The image evidence is identified, and image information included in the image evidence is identified, where the image information may be: vehicle type, body color, head, tail, license plate type, license plate color, license plate number, zebra crossing, no-stop line, sidewalk, window ticket, door status, passengers getting on and off, etc. And performing semantic conversion according to the identified image information to obtain vehicle information which is certified in the image evidence. The evidence-obtaining vehicle information in the image evidence is that text information is obtained after the image information is converted according to the semantic conversion rule, a display interface of the evidence-obtaining vehicle information in the image evidence is obtained after the image identification is performed on the image evidence as shown in fig. 6, and the image information in the image evidence is converted into the text information.
And step S260, detecting the evidence to be detected based on the evidence obtaining scene information and the evidence obtaining vehicle information according to a preset evidence detection strategy.
Wherein, the detection is to detect whether the evidence to be detected meets the requirements of evidence collection of a set case. The preset evidence detection strategy is to determine necessary information corresponding to different forensics scene information according to the different forensics scene information, and detect whether the evidence to be detected meets the requirements of case forensics according to the necessary information. According to a preset evidence detection strategy, detecting evidence to be detected based on forensics scene information and forensics vehicle information to obtain a detection result, if: the image evidence of the evidence to be detected comprises a picture A, a picture B and a picture C, and the necessary information is determined according to the evidence obtaining scene information as follows: when detecting, detecting pictures A, B and C, wherein the pictures A, B and C comprise complete vehicle head and clear license plate information, and the pictures A, B and C meet the picture comprising the information of the notification list information, so as to obtain a corresponding detection result.
And step S280, when the evidence to be detected passes the detection, taking the evidence to be detected as the traffic violation evidence.
When the evidence to be detected passes the detection, the evidence to be detected can be determined to meet the evidence obtaining requirement, and the evidence to be detected can be used as the traffic violation evidence. Such as: taking the evidence obtaining scene information as an example of vehicle illegal parking, the image evidence of the evidence to be detected needs to have at least one piece of mark information (mark information, such as zebra stripes, forbidden parking marks and the like) which needs to contain complete vehicle fronts and clear vehicle license plate information and can prove illegal parking, at least one piece of mark information (mark information, such as zebra stripes, forbidden parking marks and the like) which needs to contain notification note information, when the image evidence of the evidence to be detected meets the condition that the image evidence contains complete vehicle fronts and clear vehicle license plate information and can prove illegal parking, the image evidence of the evidence to be detected contains notification note information, and when the image evidence of the evidence to be detected contains complete vehicle fronts and clear vehicle license plate information and can prove illegal parking, the evidence to be detected passes the detection, and the evidence to be detected can be used as traffic illegal parking evidence.
According to the traffic image evidence verification method, image identification is carried out on the image evidence in the evidence to be detected uploaded by the terminal in real time, evidence obtaining vehicle information in the image evidence is obtained, evidence to be detected is detected based on evidence obtaining scene information and evidence obtaining vehicle information according to a preset evidence detection strategy, evidence auditing is completed in time, evidence which is unqualified to evidence obtaining is detected in time, evidence which is unqualified to evidence obtaining is carried out again according to the evidence which is unqualified, and the accuracy rate of vehicle image evidence collection is improved.
In one embodiment, the step of detecting the evidence to be detected based on the forensics scene information and the forensics vehicle information according to a preset evidence detection strategy includes:
determining corresponding necessary information from a preset database according to the forensics scene information; the information in the preset database is used for distinguishing necessary information corresponding to different forensics scene information; and detecting the evidence to be detected according to the necessary information and the evidence obtaining vehicle information to obtain a detection result.
The necessary information corresponding to the forensics scene information is essential information for proving that the vehicle to be forensics violates the traffic rules, and the necessary information may be one or more items, such as vehicle head information + vehicle license plate information on the vehicle head, and a zebra crossing. Taking the evidence obtaining scene information as an example that the vehicle is illegal to stop, the evidence obtaining vehicle is to be proved to be illegal to stop, the evidence obtaining vehicle must be stopped at a place where the vehicle cannot be stopped, such as a zebra crossing, a no stop crossing, a sidewalk, and the like, the vehicle body of the evidence obtaining vehicle and the environment where the evidence obtaining vehicle stops must be shot in the collected image evidence, if the evidence obtaining vehicle is a zebra crossing, the vehicle needs to be proved to stop on the zebra crossing, and necessary information needs to include: the vehicle head information, the vehicle license plate information on the vehicle head, the vehicle tail information, the vehicle license plate information on the vehicle tail, the zebra crossing and the notice. Whether the evidence to be detected meets the evidence obtaining requirement can be judged by detecting whether the evidence to be detected contains necessary information or not. The evidence to be detected is detected according to the necessary information and the evidence obtaining vehicle information, evidence which is obtained evidence and does not meet requirements can be detected in time, evidence which is not met requirements is obtained again, and the accuracy of collecting vehicle image evidence is improved.
In one embodiment, the step of detecting the evidence to be detected according to the necessary information and the information of the vehicle to be proved comprises the following steps:
searching information in the information of the vehicle to be proved according to the necessary information, and acquiring detection information corresponding to the necessary information; when each item of the necessary information has corresponding detection information, the evidence to be detected passes the detection; and when one or more items of detection information corresponding to the necessary information are missing, marking one or more items of detection information corresponding to the missing essential information, and sending the marked items of detection information to the terminal for displaying.
The detection information refers to information corresponding to necessary information in the forensic vehicle information, such as: one item of the necessary information is zebra crossing information, and the detection information is the zebra crossing information in the vehicle information for evidence collection. Each item of the necessary information has corresponding detection information, which means that each item of the necessary information has corresponding detection information in the forensic vehicle information, such as: the necessary information includes: when the vehicle information obtained by evidence collection simultaneously comprises the vehicle head information, the vehicle license plate information on the vehicle head, the vehicle tail information, the vehicle license plate information on the vehicle tail, the zebra crossing and the notification list, corresponding detection information exists for each item of necessary information.
The absence of the detection information corresponding to one or more of the necessary information means that one or more of the necessary information does not have corresponding detection information in the forensic vehicle information, such as: the necessary information includes: the vehicle information comprises vehicle head information, vehicle tail information, zebra stripes and an informing sheet, and when the vehicle information which is obtained by evidence only comprises the vehicle head information, the vehicle tail information and the vehicle tail information, the detection information corresponding to necessary information lacks the zebra stripes and the informing sheet.
Marking one or more items of detection information corresponding to the missing of the necessary information means marking all items of detection information corresponding to the missing of the necessary information, when the detection information corresponding to the missing of the necessary information is one item, the corresponding mark lacks the item of detection information corresponding to the missing of the necessary information, and when the detection information corresponding to the missing of the necessary information is multiple items, the corresponding mark lacks multiple items of detection information corresponding to the missing of the necessary information, such as: if the zebra crossing and the notice sheet which lack the corresponding detection information in the necessary information are missing, the zebra crossing and the notice sheet are marked and sent to a terminal for displaying so as to remind traffic police personnel of the missing information of the evidence to be detected. By marking one or more items of detection information which is missing corresponding to the necessary information, traffic police personnel can know in time where the evidence to be detected does not meet the evidence obtaining requirement, and can only modify the evidence which does not meet the evidence obtaining requirement in the evidence to be detected, so that the evidence obtaining efficiency can be improved.
In one embodiment, the step of identifying the image evidence and obtaining the vehicle information for evidence collection in the image evidence includes:
carrying out image recognition on the image evidence through an image recognition model to obtain image information; and performing semantic conversion according to the image information to obtain the evidence obtaining vehicle information.
The image recognition model is designed based on a neural network and has the capability of processing, analyzing and understanding the image. The content of image recognition of the image evidence comprises the following steps: vehicle identification: vehicle type identification (ordinary car, SUV, small/medium/large truck, special vehicle (ambulance, police car), etc.), vehicle body color identification, vehicle head detection (whether the angle of the shot vehicle is the vehicle head), vehicle tail detection (whether the angle of the shot vehicle is the vehicle tail), etc., license plate identification: license plate type recognition, license plate color recognition, license plate number recognition and the like. Object detection: zebra crossing, no-stop line, sidewalk detection, vehicle window ticket detection, vehicle door state detection, passenger getting on and off, and the like. The image identification is carried out on the image evidence based on the image identification model, so that manual image evidence review can be replaced, and the review efficiency is improved.
In one embodiment, the step of obtaining image information by performing image recognition on the image evidence through an image recognition model includes:
the image recognition model carries out image recognition on the image evidence according to the attribute of the image evidence to obtain image information; when the attribute of the image evidence is a scene image, the image recognition model recognizes the vehicle attribute, the license plate and the environment to obtain license plate data, vehicle attribute data and environment data; taking vehicle attribute data, the license plate data and environment data as image information; when the attribute of the image evidence is a notice image, the image recognition model recognizes the notice image to obtain notice information; the notification sheet information is used as picture information.
The attributes of the image evidence include a scene image, a notice sheet image and the like, wherein the scene image refers to an image containing a vehicle to be proved, the notice sheet image refers to a paper notice sheet image, and the notice sheet can be a ticket and the like. The vehicle attribute data refers to a vehicle type (a general car, an SUV, a small/medium/large truck, a special vehicle (an ambulance, a police car), etc.), a vehicle body color, a vehicle head (a photographed vehicle angle is a vehicle head), a vehicle tail (a photographed vehicle angle is a vehicle tail), etc. The license plate data refers to license plate type, license plate color, license plate number and the like. The environmental data refers to zebra crossing, no-stop line, sidewalk, window ticket, door status, passengers getting on or off the bus, etc. The image recognition model recognizes the notice sheet image to obtain notice sheet information, namely, whether the notice sheet image is a notice sheet or not is recognized, and the notice sheet information is a notice sheet image or a non-notice sheet image. And image recognition is carried out on the image evidence through the image recognition model according to the attribute of the image evidence, image information is obtained, whether the image evidence meets the evidence obtaining requirement is determined, and the evidence obtaining efficiency is improved.
In one embodiment, after the step of using the evidence to be detected as the evidence of traffic violation when the detection result is passing, the method further comprises:
acquiring law enforcement information according to the traffic law violation evidence; and establishing the illegal case according to the law enforcement information and the traffic violation evidence.
Wherein, law enforcement information includes: the law enforcement information can be input by policemen through a terminal, can be the illegal place of the vehicle to be forensic acquired by the terminal according to the current positioning function, and can be the law enforcement policemen information acquired according to the account information of the current law enforcement account. The server establishes the illegal case after acquiring the law enforcement information uploaded by the policemen through the terminal and the traffic violation evidence, and stores all data of the illegal case into a database, wherein all data of the illegal case comprise the law enforcement information, the traffic violation evidence and the like. The evidence to be detected is checked in real time, so that the traffic law violation evidence meeting the evidence obtaining requirement can be determined in time, the case violation is set up in time, and the work efficiency of setting up the case is improved.
In one embodiment, the method further comprises:
when a vehicle information query instruction is received, acquiring corresponding content according to query content in the vehicle query instruction, and sending the corresponding content to a terminal, wherein the query content comprises vehicle illegal information query and/or vehicle archive information query.
Wherein, the inquiry content can be vehicle illegal information inquiry, also can be vehicle archives information inquiry, can also be vehicle illegal information inquiry and vehicle archives information inquiry, through the vehicle license plate number inquiry vehicle archives information, if: owner information and vehicle registration information (brand, color, vehicle type, vehicle usage, etc.). And inquiring vehicle file information of the passing vehicle to assist law enforcement. Inquiring vehicle illegal information through the license plate number, such as: historical time of violation, location of violation, and corresponding violation of the vehicle. The vehicle law violation information can be inquired whether meeting the non-penalty condition according to local traffic laws and regulations, and if the vehicle is violated for multiple times in a local short time, the vehicle can be marked as a control vehicle to pay important attention. When the related information of the vehicle to be proved is required to be acquired in the law enforcement process, the corresponding information can be acquired in time through the query function, and the law enforcement efficiency can be improved.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least some of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 7, there is provided a traffic image evidence verification apparatus including: the evidence obtaining module 310 to be detected, the image evidence recognition module 320, the detection module 330, and the illegal evidence confirmation module 340, wherein:
the evidence obtaining module 310 is configured to obtain an evidence to be detected uploaded by the terminal, where the evidence to be detected includes an image evidence and forensics scene information.
And the image evidence identification module 320 is configured to identify the image evidence and obtain the vehicle information for forensics in the image evidence.
The detection module 330 is configured to detect the evidence to be detected based on the forensics scene information and the forensics vehicle information according to a preset evidence detection strategy.
And the illegal evidence confirmation module 340 is configured to, when the to-be-detected evidence passes the detection, use the to-be-detected evidence as the traffic illegal evidence.
In one embodiment, the detection module 330 is further configured to: determining corresponding necessary information from a preset database according to the forensics scene information; the information in the preset database is used for distinguishing necessary information corresponding to different forensics scene information; and detecting the evidence to be detected according to the necessary information and the information of the vehicle to be proved.
In one embodiment, the detection module 330 is further configured to: searching information in the information of the vehicle to be proved according to the necessary information, and acquiring detection information corresponding to the necessary information; when each item of the necessary information has corresponding detection information, the evidence to be detected passes the detection; and when one or more items of detection information corresponding to the necessary information are missing, marking one or more items of detection information corresponding to the missing essential information, and sending the marked items of detection information to the terminal for displaying.
In one embodiment, the image evidence identification module 320 is further configured to: carrying out image recognition on the image evidence through an image recognition model to obtain image information; and performing semantic conversion according to the image information to obtain the evidence obtaining vehicle information.
In one embodiment, the image evidence identification module 320 is further configured to: the image recognition model carries out image recognition on the image evidence according to the attribute of the image evidence to obtain image information; when the attribute of the image evidence is a scene image, the image recognition model recognizes the vehicle attribute, the license plate and the environment to obtain license plate data, vehicle attribute data and environment data; taking vehicle attribute data, the license plate data and environment data as image information; when the attribute of the image evidence is the notice sheet image, the image recognition model recognizes the notice sheet image to obtain notice sheet information; the announcement information is used as picture information.
As shown in fig. 8, in one embodiment, the traffic image evidence verification apparatus further includes: a protocol module 350 for acquiring law enforcement information according to the evidence of traffic violation; and establishing the illegal case according to law enforcement information and the traffic violation evidence.
In one embodiment, the traffic image evidence verification apparatus further includes: and the query module 360 is configured to, when a vehicle information query instruction is received, obtain corresponding content according to query content in the vehicle query instruction, and send the corresponding content to the terminal, where the query content includes vehicle illegal information query and/or vehicle archive information query.
Above-mentioned traffic image evidence verifying attachment, through waiting to detect the evidence that detects that the evidence acquisition module 310 acquires that the terminal uploads waits to detect, image evidence identification module 320 acquires in real time that the terminal uploads waits to detect the image evidence in the evidence and carries out image recognition, obtain the vehicle information that forensics in the image evidence, detection module 330 is according to preset evidence detection strategy, based on scene information and the vehicle information that forensics, the evidence that waits to detect detects, illegal evidence confirmation module 340 when the testing result is for passing through, will wait to detect the evidence that detects as the illegal evidence of traffic, thereby in time accomplish evidence audit, in time detect out the evidence that forensics is not qualified, forensics again to the evidence that is not qualified, the rate of accuracy of collecting vehicle image evidence has been improved.
For specific limitations of the traffic image evidence verification device, reference may be made to the above limitations of the traffic image evidence verification method, which are not described herein again. The modules in the traffic image evidence verification device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store image evidence data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a traffic image evidence verification method.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
acquiring evidence to be detected uploaded by a terminal, wherein the evidence to be detected comprises image evidence and evidence obtaining scene information; identifying the image evidence to obtain the vehicle information which is obtained by evidence collection in the image evidence; detecting evidence to be detected based on forensics scene information and forensics vehicle information according to a preset evidence detection strategy; and when the evidence to be detected passes the detection, taking the evidence to be detected as the traffic violation evidence.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining corresponding necessary information from a preset database according to the forensics scene information; the information in the preset database is used for distinguishing necessary information corresponding to different forensics scene information; and detecting the evidence to be detected according to the necessary information and the information of the vehicle to be proved.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
searching information in the information of the vehicle to be proved according to the necessary information, and acquiring detection information corresponding to the necessary information; when each item of the necessary information has corresponding detection information, the evidence to be detected passes the detection; and when one or more items of detection information corresponding to the necessary information are missing, marking one or more items of detection information corresponding to the missing essential information, and sending the marked items of detection information to the terminal for displaying.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out image recognition on the image evidence through an image recognition model to obtain image information; and performing semantic conversion according to the image information to obtain the evidence obtaining vehicle information.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
the image recognition model carries out image recognition on the image evidence according to the attribute of the image evidence to obtain image information; when the attribute of the image evidence is a scene image, the image recognition model recognizes the attribute of the vehicle, the license plate and the environment to obtain license plate data, vehicle attribute data and environment data; taking vehicle attribute data, the license plate data and environment data as image information; when the attribute of the image evidence is the notice sheet image, the image recognition model recognizes the notice sheet image to obtain notice sheet information; the announcement information is used as picture information.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring law enforcement information according to the traffic law violation evidence; and establishing the illegal case according to law enforcement information and the traffic violation evidence.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
when a vehicle information query instruction is received, acquiring corresponding content according to query content in the vehicle query instruction, and sending the corresponding content to a terminal, wherein the query content comprises vehicle illegal information query and/or vehicle archive information query.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring evidence to be detected uploaded by a terminal, wherein the evidence to be detected comprises image evidence and evidence obtaining scene information; identifying the image evidence to obtain the vehicle information which is obtained by evidence collection in the image evidence; detecting evidence to be detected based on forensics scene information and forensics vehicle information according to a preset evidence detection strategy; and when the evidence to be detected passes the detection, taking the evidence to be detected as the traffic violation evidence.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining corresponding necessary information from a preset database according to the forensics scene information; the information in the preset database is used for distinguishing necessary information corresponding to different forensics scene information; and detecting the evidence to be detected according to the necessary information and the information of the vehicle to be proved.
In one embodiment, the computer program when executed by the processor further performs the steps of:
searching information in the information of the vehicle to be proved according to the necessary information, and acquiring detection information corresponding to the necessary information; when each item of the necessary information has corresponding detection information, the evidence to be detected passes the detection; and when one or more items of detection information corresponding to the necessary information are missing, marking one or more items of detection information corresponding to the missing essential information, and sending the marked items of detection information to the terminal for displaying.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out image recognition on the image evidence through an image recognition model to obtain image information; and performing semantic conversion according to the image information to obtain the evidence obtaining vehicle information.
In one embodiment, the computer program when executed by the processor further performs the steps of:
the image recognition model carries out image recognition on the image evidence according to the attribute of the image evidence to obtain image information; when the attribute of the image evidence is a scene image, the image recognition model recognizes the attribute of the vehicle, the license plate and the environment to obtain license plate data, vehicle attribute data and environment data; taking vehicle attribute data, the license plate data and environment data as image information; when the attribute of the image evidence is the notice sheet image, the image recognition model recognizes the notice sheet image to obtain notice sheet information; the announcement information is used as picture information.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring law enforcement information according to the traffic law violation evidence; and establishing the illegal case according to law enforcement information and the traffic violation evidence.
In one embodiment, the computer program when executed by the processor further performs the steps of:
when a vehicle information query instruction is received, acquiring corresponding content according to query content in the vehicle query instruction, and sending the corresponding content to a terminal, wherein the query content comprises vehicle illegal information query and/or vehicle archive information query.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (10)
1. A traffic image evidence validation method, the method comprising:
when a evidence obtaining control is triggered through an interface of a terminal for uploading evidence to be detected, the evidence to be detected uploaded by the terminal is obtained, and the evidence to be detected comprises image evidence and manually selected evidence obtaining scene information;
identifying the image evidence to obtain the information of the vehicle which is subjected to evidence obtaining in the image evidence;
determining corresponding necessary information from a preset database according to the forensics scene information; the information in the preset database is used for distinguishing the necessary information corresponding to different forensics scene information; the forensics scene information refers to the type of traffic rules violated by the forensics vehicle; the necessary information is used for detecting whether the evidence to be detected meets the requirements of case evidence collection;
detecting the evidence to be detected according to the necessary information and the evidence obtaining vehicle information;
and when the evidence to be detected passes the detection, taking the evidence to be detected as the evidence of traffic violation.
2. The method according to claim 1, wherein the step of detecting the evidence to be detected based on the essential information and the forensic vehicle information comprises:
searching information in the evidence-obtaining vehicle information according to the necessary information, and acquiring detection information corresponding to the necessary information;
when each item of the necessary information has corresponding detection information, the evidence to be detected passes the detection;
and when one or more items of detection information corresponding to the necessary information are missing, marking one or more items of detection information corresponding to the missing essential information, and sending the marked items of detection information to a terminal for displaying.
3. The method according to claim 1, wherein the step of identifying the image evidence and obtaining the vehicle information for evidence in the image evidence comprises:
carrying out image recognition on the image evidence through an image recognition model to obtain image information;
and performing semantic conversion according to the image information to obtain the evidence obtaining vehicle information.
4. The method according to claim 3, wherein the step of performing image recognition on the image evidence through an image recognition model to obtain image information comprises:
the image recognition model carries out image recognition on the image evidence according to the attribute of the image evidence to obtain image information;
when the attribute of the image evidence is a scene image, the image recognition model recognizes the attribute of the vehicle, the license plate and the environment to obtain license plate data, vehicle attribute data and environment data;
taking the vehicle attribute data, the license plate data and the environment data as image information;
when the attribute of the image evidence is a notice sheet image, the image recognition model recognizes the notice sheet image to obtain notice sheet information;
and taking the notification list information as picture information.
5. The method according to claim 1, wherein when the detection result is pass, the step of using the evidence to be detected as the evidence of traffic violation is followed by further comprising:
acquiring law enforcement information according to the traffic law violation evidence;
and establishing an illegal case according to the law enforcement information and the traffic violation evidence.
6. The method according to any one of claims 1-5, further comprising:
when a vehicle information query instruction is received, acquiring corresponding content according to query content in the vehicle information query instruction, and sending the corresponding content to a terminal, wherein the query content comprises vehicle illegal information query and/or vehicle archive information query.
7. An apparatus for verifying traffic image evidence, the apparatus comprising:
the evidence obtaining module to be detected is used for obtaining evidence to be detected uploaded by the terminal when the evidence obtaining control is triggered through an interface of the terminal for uploading the evidence to be detected, wherein the evidence to be detected comprises image evidence and manually selected evidence obtaining scene information;
the image evidence identification module is used for identifying the image evidence to obtain the evidence-obtaining vehicle information in the image evidence;
the detection module is used for determining corresponding necessary information from a preset database according to the forensics scene information; the information in the preset database is used for distinguishing the necessary information corresponding to different forensics scene information; the forensics scenario information refers to the type of traffic rules violated by the forensics vehicle; the necessary information is used for detecting whether the evidence to be detected meets the requirements of case evidence collection;
detecting the evidence to be detected according to the necessary information and the evidence obtaining vehicle information;
and the illegal evidence confirmation module is used for taking the to-be-detected evidence as the traffic illegal evidence when the to-be-detected evidence passes the detection.
8. The device according to claim 7, wherein the detection module is further configured to perform information lookup on the forensic vehicle information according to the necessary information, and acquire detection information corresponding to the necessary information; when each item of the necessary information has corresponding detection information, the evidence to be detected passes the detection; and when one or more items of detection information corresponding to the missing essential information are missing, marking one or more items of detection information corresponding to the missing essential information, and sending the marked items of detection information to a terminal for displaying.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010129265.7A CN111462480B (en) | 2020-02-28 | 2020-02-28 | Traffic image evidence verification method and device, computer equipment and storage medium |
| PCT/CN2020/097647 WO2021169097A1 (en) | 2020-02-28 | 2020-06-23 | Traffic image evidence verification method, apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010129265.7A CN111462480B (en) | 2020-02-28 | 2020-02-28 | Traffic image evidence verification method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111462480A CN111462480A (en) | 2020-07-28 |
| CN111462480B true CN111462480B (en) | 2023-02-07 |
Family
ID=71679961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010129265.7A Active CN111462480B (en) | 2020-02-28 | 2020-02-28 | Traffic image evidence verification method and device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111462480B (en) |
| WO (1) | WO2021169097A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117033532A (en) * | 2023-07-20 | 2023-11-10 | 长江信达软件技术（武汉）有限责任公司 | Wading problem evidence obtaining method, wading problem evidence obtaining equipment and storage equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484395A (en) * | 2014-12-12 | 2015-04-01 | 西安酷派软件科技有限公司 | Vehicle violation query method, vehicle violation disposal method, vehicle violation query system and vehicle violation disposal system |
| CN104952255A (en) * | 2015-06-25 | 2015-09-30 | 上海卓易科技股份有限公司 | Intelligent terminal as well as traffic violation monitoring method and system thereof |
| CN109949579A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method that makes a dash across the red light based on deep learning |
| CN109949569A (en) * | 2019-02-18 | 2019-06-28 | 广东中标数据科技股份有限公司 | A kind of traffic violation data auditing system and its implementation |
| CN110717433A (en) * | 2019-09-30 | 2020-01-21 | 华中科技大学 | Deep learning-based traffic violation analysis method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620782A (en) * | 2008-06-30 | 2010-01-06 | 深圳富泰宏精密工业有限公司 | Regulation-violating behaviour evidence-obtaining system and method therefor |
| US20100157061A1 (en) * | 2008-12-24 | 2010-06-24 | Igor Katsman | Device and method for handheld device based vehicle monitoring and driver assistance |
| CN103531026A (en) * | 2013-09-22 | 2014-01-22 | 郑恒强 | Mobile intelligent terminal and mobile internet technology-based road violation forensic system |
| CN105070061B (en) * | 2015-08-19 | 2017-09-29 | 王恩琦 | Vehicle peccancy evidence obtaining checking method and its system |
| CN106327878A (en) * | 2016-11-16 | 2017-01-11 | 天津市中环***工程有限责任公司 | Movable illegal parking snapshot system and implementation method |
-
2020
- 2020-02-28 CN CN202010129265.7A patent/CN111462480B/en active Active
- 2020-06-23 WO PCT/CN2020/097647 patent/WO2021169097A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484395A (en) * | 2014-12-12 | 2015-04-01 | 西安酷派软件科技有限公司 | Vehicle violation query method, vehicle violation disposal method, vehicle violation query system and vehicle violation disposal system |
| CN104952255A (en) * | 2015-06-25 | 2015-09-30 | 上海卓易科技股份有限公司 | Intelligent terminal as well as traffic violation monitoring method and system thereof |
| CN109949579A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method that makes a dash across the red light based on deep learning |
| CN109949569A (en) * | 2019-02-18 | 2019-06-28 | 广东中标数据科技股份有限公司 | A kind of traffic violation data auditing system and its implementation |
| CN110717433A (en) * | 2019-09-30 | 2020-01-21 | 华中科技大学 | Deep learning-based traffic violation analysis method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111462480A (en) | 2020-07-28 |
| WO2021169097A1 (en) | 2021-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106710291B (en) | Parking space obtaining method and device for parking lot | |
| CN108540579B (en) | Driver identity online monitoring method and device and storage medium | |
| JP5260504B2 (en) | Verification engine, method, data processing system (validation engine) | |
| US9336450B2 (en) | Methods and systems for selecting target vehicles for occupancy detection | |
| CN109523652B (en) | Insurance processing method, device and equipment based on driving behaviors and storage medium | |
| CN108090747B (en) | Self-service vehicle checking method, device, equipment and computer storage medium for vehicle insurance underwriting | |
| CN111079751B (en) | Method and device for identifying authenticity of license plate, computer equipment and storage medium | |
| WO2021184570A1 (en) | Method and apparatus for identifying driving behaviors of electric bicycle, and computer device | |
| CN107111940B (en) | Traffic violation management system and traffic violation management method | |
| CN110929589A (en) | Method, device, computer device and storage medium for vehicle feature recognition | |
| CN108932850B (en) | Method and device for recording low-speed driving illegal behaviors of motor vehicle | |
| EP3642793A1 (en) | Platform for the management and validation of contents of video images, pictures or similars, generated by different devices | |
| CN107004352B (en) | Traffic violation management system and traffic violation management method | |
| KR101066081B1 (en) | Smart information detection system mounted on the vehicle and smart information detection method using the same | |
| CN115810134A (en) | Image acquisition quality inspection method, system and device for preventing car insurance from cheating | |
| CN111462480B (en) | Traffic image evidence verification method and device, computer equipment and storage medium | |
| CN108417045A (en) | A kind of comity pedestrian captures processing system and its method | |
| JP2006119767A (en) | Illegal vehicle information system, controlling server and illegal vehicle information program | |
| CN110706115A (en) | Traffic accident fast claims settlement method, system and server | |
| CN111368626B (en) | Vehicle identification method, device, electronic equipment and storage medium | |
| JP2005301377A (en) | Vehicle reference system and vehicle reference method for it | |
| CN113781792B (en) | Parking detection system, method and related equipment | |
| CN114882448A (en) | Vehicle monitoring method and electronic equipment | |
| CN110933360A (en) | Vehicle violation monitoring method and system | |
| CN112906486B (en) | Passenger condition detection method, control method and system for unmanned taxi |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |